Download December2011

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Probability wikipedia , lookup

History of statistics wikipedia , lookup

Statistics wikipedia , lookup

Transcript
No. of Printed Pages : 11
I MIA 002 (F2F)
-
M.Sc. ACTUARIAL SCIENCE
Cr)
0)
Term-End. Examination
December, 2011
CIO
MIA-002 (F2F) : PROBABILITY AND
MATHEMATICAL STATISTICS
Time : 3 hours
Maximum Marks : 100
Students are allowed to use scientific calculator and
Note :
actuarial tables.
SECTION A
Attempt any five questions.
1.(a) The following data represent the scores
obtained by 27 students in a mid-term test :
79, 78, 78, 67, 76, 87, 85, 73, 66,
99, 84, 72, 66, 57, 94, 84, 72, 63,
51, 48; 50, 61, 71, 82, 93, 100, 89,
(i)
Prepare stern and leaf display of the 3
data.
(ii) Calculate the range and the inter 2
quartile range.
(b) The ages in year of a group of 20 individuals 3
are as follows :
50, 56, 55, 49, 52, 57, 56, 57, 56, 59,
54, 55, 61, 60, 51, 59, 62, 52, 54, 49
-
If X denotes the mean and s the standard
deviation of the sample, find the percentage
of items failing within the interval X ± s
(Given Ix =1104
/x2 =61226)
MIA 002 (F2F)
-
1
P.T.O.
2.A random sample (x ix2, xn) is taken from a
Poisson distribution, with parameter
(a) Show that the maximum likelihood
estimator of 1.1. is :
A
=
(b)
Obtain the bias and mean square error
of (c)
X
*
A
Show that the variance of attains the
Cramer - Rao lower bound.
3.(a) In an insurance company, three actuarial
assistants A, B and C are assigned to process
loan application forms against the policies.
A processes 40%; B processes 35% ; and C
processes 25% of the loan applications. The
error rate while processing the loan
applications by A, B and C are 0.04, 0.06
and 0.03 respectively. A loan application
selected at random by the Branch manager
is found to have an error. What is the
probability that it was processed by A ?
(b) If the probability is 0.20 that a certain bank
will refuse a loan application, using normal
approximation (to three decimals), find the
probability that the bank will refuse at most
40 out of 225 loan applications.
MIA-002 (F2F)
2
4.
The Gamma distribution with parameters a and
A, has moment generating function :
M X(t) = 11 — Itl a
(a)
(b)
Show, using moment generating function,
that the sum of two independent Gamma
distributions, each with parameter A, is also
a Gamma distribution.
A random sample X 1 , X2 X„ is taken from
a Gamma (a, A) distribution. Derive the
moment generating function of 2X 1:x i and
hence show tharltortas a x z2 „ distribution.
(c)
Suppose that X is the mean of a random
sample of size 5 taken from a Gamma
(2, 0.1) distribution. Use the result from part
(b) to calculate the probability that 5(
exceeds 40.
5.A large office has n policyholders, each with a
probability of 0.01 of dying during the next year
(independently of all other policyholders).
Calculate the approximate probability that these
will be between 9 and 16 (both inclusive) deaths
during the year, when :
(a) n = 400
(b) n = 3,000
MIA-002 (F2F)
3
4
4
P.T.O.
6.The joint pmf of x and y is given below.
Y
0
1
2
x
0
1/6
2/9
1/36
1
1/3
1/6
0
2
1/12
0
0
find :
(a)
Mean values of X and Y.
(b)
Find the covariance between X and Y. 1
(c)
Conditional distribution of X given Y 1. 2
(d)
Correlation between X and Y. 2
3
7.A survey was conducted to investigate whether
people tend to marry partners of about the same
age. This question was addressed to 12 married
couples and their ages were given in the following
table.
Couple No. 1 2 3 4 5 6 7 8 9 10 11 12
Husband's
30 29 36 72 37 36 51 48 37 50 51 36
age (x)
Wife's age
27 20 34 67 35 37 50 46 36 42 46 35
(y)
(a)
Draw the scatter plot and comment on it. 1
(b)
Find the correlation coefficient and interpret 4
it.
(c)
If p represent the population correlation 3
coefficient between the ages of partners, test
the significance of p at 5% level.
MIA-002 (F2F)
4
SECTION - B
Attempt any four questions.
8.(a) (i)State the central limit theorem.2
(ii) What is the approximate distribution 3
of the arithmetic mean of a set of 100
independent observations from a
Gamma (2.5, 0.2) distribution ?
(b) House's prices, in region X are normally
distributed about a mean of Rs. 1,00,000
with a standard deviation of Rs. 10,000.
House prices in region Y are normally
distributed about a mean of Rs. 90,000 with
a standard deviation'of Rs. 5,000. A sample
of 10 houses is taken from region X and a
sample of 5 houses from region Y, Find the
probability that :
(i)
the region X sample mean is greater
than the region Y sample mean.
(ii)
the difference between the sample
mean is less than 5,000.
(iii) the region X sample variance is less
than the region Y sample variance.
5
5
(iv) the region X sample standard
deviation is more than four times
greater than the region Y sample
standard deviation.
MIA-002 (F2F)
5
P.T.O.
9.(a) Eight pairs of slow learners with similar
reading capabilities are identified in a third
grade class. One member of each pair is
randomly assigned to the standard teaching
method, while the other is assigned to a new
teaching method. The scores are as given
below.
Pair
1 2 3 4 5 6 7 8
New method 77 74 82 73 87 69 66 80
Old method 72 68 76 68 84 68 64 76
(i)
Test for the difference between mean 6
scores for the two methods.
(ii)
Test for the equality of variances for 4
these two methods.
(b) The diameter of steel rods manufactured on
two different machines A and B is studied.
Two random samples of sizes n1 =12 and
n2 =15 are selected and the sample means
and sample standard deviations respectively
are : x1 = 24.6 , S 1 = 0.85
= 22.1 , S2 = 0.98
Assuming that the diameters of the rods are
as follow N(ll, cr2) and N(12, cr2 ),
MIA-002 (F2F)
(i)
Test the equality of means of the 3
diameters of the rods manufactured
by the two machines assuming
22
1 =Q2
(ii)
Construct 95% confidence interval for 2
[Li —1.L2 assuming
10.
pi = 0•3 •
Two thousand individuals were choosen at
random by a researcher and cross classified
according to gender and colour blindness as given
below :
Description
Normal
Colour Blind
(a)
Male
904
91
Female
998
7
Apply an appropriate test to conclude that 4
there is overwhelming evidence against the
hypothesis that there is no association
between gender and colour blindness.
(b)
A genetic model states that the human
population is split in the proportion as
illustrated in the following table where
q (0<q<1) is a parameter related to the
distribution of the colour blindness.
MIA-002 (F2F)
7
P.T.O.
Description
Normal
Male
Female
(1 — q)/2 (1
Colour Blind
q/2
—
q2)/2
q2 /2
Using the data in a) :
11.
(i)
Write down the likelihood function for 3
the above model.
(ii)
Determine the maximum likelihood 8
estimate of q.
An actuary has been advised to use the following
positively - skewed claim size distribution as a
model for a particular type of claim, with claim
sizes measured in units of Rs. 100
2
X(— X
f(X e) = 20 3 exP t) ° < x <
, 0>0
with moments given by E(x) = 30, E(x 2) = 120 2 and
E(x3) = 6003 .
(a)
Determine the variance of this distribution 4
and calculate the coefficient of skewness.
(b)
Let X1, X2 Xn be a random sample of n 5
claim sizes for such claims.
Show that the maximum likelihood
estimator (MLE) of 0 is given bye
show that it is unbiased for 0.
MIA-002 (F2F)
8
=3
and
(c) A sample of n=50 claim sizes yields
= 313.6 and sx? = 2,675.68.
(i)
Calculate the MLE g
(ii)
Calculate the sample variance and 2
.
comment briefly on its comparison
with the variance of the distribution
evaluated at
(iii)
8.
Given that the sample coefficient of 2
skewness is 1.149, comment briefly on
its comparison with the coefficient of
skewness of the distribution.
12. A humidity influences evaporation, the solvent
balance of water - reducible paints during sprayout is affected by humidity. A study is conducted
to examine the relation between humidity (X) and
the extent of solvent evaporation (Y). The
following data summary is obtained :
n=25, Z.x. =1314.90, Zy = 235.70
ix2 = 76,308.53, ly 2 = 2286.07
/xy =11,824.44
(a) Find the estimated correlation coefficient 4
between X and Y and test the hypothesis
Ho : p = 0, against H1 : p#0 ; p being the
population correlation coefficient between
X and Y.
MIA-002 (F2F)
9
P.T.O.
(b)
Stating the assumptions, fit a regression line 3
of the model yi =130 +13ixi + ei for the above
data.
(c)
Obtain the unbiased estimator of 0-2.2
(d)
Test the hypothesis H 0 :
ft =0 against3
H1 :
(e)
Obtain 90% confidence interval for 13 0 and
99% confidence interval for
pi .
13. Three different drugs are being compared for their
effectiveness in treating a certain illness. The mean
number of days before the patient is discharged
from hospital under each treatment is summarised
below, together with the sample size and the sum
of squares of the observations :
Treatment Sample size
Sample sum of
mean
squares
A
10
5
264
B
6
7
310
C
8
3
84
(a) For these three treatments, calculate 4
estimates for the :
(i)
overall mean
(ii)
common underlying variance.
MIA-002 (F2F) 10
(b)
Perform an analysis of variance to show 5
that real differences exist among the three
treatments at the 1% level.
(c)
Show that the mean number of days before 3
discharge under treatments A is
significantly better than under treatment
B.
(d)
The cost per day for treatments A, B and 3
C are Rs. 7.50, Rs. 5.85, Rs. 14.95
respectively. Given that it can also be
shown that there are significant differences
between each pair of treatments, briefly
advise the hospital on which treatment it
should use.
MIA-002 (F2F) 11